--- title: DMCRA Elastic Centroid Lab emoji: ๐Ÿงช colorFrom: purple colorTo: blue sdk: static app_file: index.html pinned: false license: mit short_description: Elastic per-block level-set quantization, measured --- # DMCRA Lab โ€” elastic per-block level sets, measured on real weights A client-side lab for the **Dynamic Multi-Centroid Routing Architecture** idea: instead of a fixed ternary grid `{-1,0,+1}` on every weight, let the *codebook itself* be chosen per block from a nested family (`{+-1}` โ†’ `{0,+-1}` โ†’ `{0,+-1,+-2}` โ†’ โ€ฆ) under a bit budget. It runs the real llama forward pass over the real weight bytes of a real GGUF, in your browser, and reports what each choice costs. No server, no GPU, no upload, no CDN, no build step. Every figure is measured on your machine. ## What it measures 1. **The level-set ladder** โ€” `binary`, `quad`, `ternary`, `penta`, `hepta`, `oct`, `nona`, each run through the real pass. Reported: the pass's own measured bits/weight, reconstruction RMSE, the mean rank of the true next token, top-1, and Spearman rho of all 512 logits against the exact pass. 2. **The multi-channel zero** โ€” `{0}` vs the document's `{0/0/0}`, compared logit by logit for exact equality. Reported whichever way it comes out. 3. **Elastic allocation at equal bits** โ€” a per-block plan that unclamps the most important blocks to the 3-bit grid and clamps the least important to the 1-bit grid, held to exactly 2.0000 index bits per weight, measured against uniform ternary at the same budget. The panel prints `UNDECIDED` when the difference is smaller than the run can resolve. ## Verdicts (Node suite, 89 scored positions) | claim | measured | |---|---| | elastic unclamping beats uniform spending at equal bits | **not supported** โ€” every keyed plan was worse (+46 to +147 rank positions, \|t\| 3.2-5.8) | | the keys still matter | **supported** โ€” keyed plans scored rho 0.52-0.55 against a key-free control's 0.06 | | `{0/0/0}` is an information channel | **refuted exactly** โ€” bit-identical logits, an extra index bit charged | | the zero-free grid at equal bits (`quad`) | **supported** โ€” rho 0.8659 vs ternary's 0.8359 at the same 2 index bits | | per-block least-squares scales | **the largest effect found** โ€” ternary rho 0.5248 โ†’ 0.8359 | Per-claim detail, including what a static page structurally cannot test (memristive, photonic and in-DRAM claims): `reports/dmcra-verdicts.md`. ## Verified 25 quantiser assertions (including that this project's ternary reproduces the sibling project's already-verified `toTernary` exactly), 21 end-to-end forward-pass assertions, and 22 assertions driving this exact page through a stubbed DOM โ€” refusing an over-ceiling model, refusing an empty prompt, and reporting an under-powered comparison as undecided rather than as a result. Part of the AEUPH studio.